A4 Conference proceedings

A hybrid method for short-term electricity consumption prediction


Publication Details

Authors: Gao Xiao Zhi, Kaarna Arto, Lensu Lasse, Honkapuro Samuli

Publication year: 2017

Language: English

Title of parent publication: IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society

ISBN: 978-1-5386-1128-9

eISBN: 978-1-5386-1127-2

JUFO level of this publication: 1

Digital Object Identifier (DOI): http://dx.doi.org/10.1109/IECON.2017.8217295

Permanent website address: http://ieeexplore.ieee.org/document/8217295/

Open Access: Not an Open Access publication


Abstract

Electricity consumption prediction is an important but demanding issue
in the study of power systems. It is difficult for the conventional
prediction methods, such as linear models, to utilize relevant domain
knowledge in the forecasting of power peaks. In this paper, we propose
an approach merging a regression predictor and a peak compensator
together. The latter is designed to compensate for the prediction errors
related to power peaks caused by the former. The proposed hybrid
short-term prediction scheme has been demonstrated in a real-world case
study to efficiently yield performances moderately better than the
standalone regression predictors.


Last updated on 2018-19-10 at 07:55